© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66739
    Prev
    Next
    INDEX
    Explanations

    system turn markers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    šku
    0.42
    ština
    0.42
    ška
    0.40
    Sis
    0.38
     sis
    0.38
    šo
    0.36
    ñ
    0.36
    čnosti
    0.36
    ŋ
    0.36
     योगी
    0.35
    POSITIVE LOGITS
    OA
    0.45
    OI
    0.44
    АК
    0.41
    OE
    0.41
    মূ
    0.40
    ઓ
    0.39
    OJ
    0.38
    INCREMENT
    0.38
    casualties
    0.37
    impression
    0.37
    Activations Density 0.030%

    No Known Activations